search

zhongkaifu / Seq2SeqSharp

Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transformer, LSTM, BiLSTM and so on), multi-GPUs supported, cross-platforms (Windows, Linux, x86, x64, ARM), multimodal model for text and images and so on.
Other
193 stars 38 forks source link

Train with general sequences of symbols #65

Closed iansmirlis closed 1 year ago

iansmirlis commented 1 year ago

Hello

It's not quite obvious for me from the documentation or the examples if Seq2SeqSharp is capable of handling generic sequences that are not necessarily language words, and if yes, how can achieve this. (I.e. tokens may not be separated by space)

Thanks

zhongkaifu commented 1 year ago

Hi @iansmirlis

Yes, Seq2SeqSharp is able to handle generic sequences. For tokens may not be separated by space, you need to find a tokenizer, such as SentencePiece (https://github.com/google/sentencepiece) to tokenize your dataset and then process it by Seq2SeqSharp.

For other types of data set, such as image, you need to read pixels from source, build vectors (tensor) for these pixels and then send it to Seq2SeqSharp for processing.

Thanks Zhongkai Fu

iansmirlis commented 1 year ago

Great! Thanks for your prompt reply